Abstract
In this paper, a delay prediction algorithm based on bidirectional associative memory neural network is proposed. The algorithm firstly uses RTT similarity to define and establish the delay function of router processing. Then, the random coefficient and other parameters of uncertain factors such as network congestion rate and network delay are calculated, to establish the prediction model of network delay. Then, the bidirectional associative memory neural network algorithm is combined with the normal distribution, and the obtained model is input to get the network delay law. The experimental results show that the proposed algorithm can predict the network delay with high accuracy, and is a feasible prediction algorithm.